Skills Drill 4

library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

Recoding Health, Sex, and BMI Variables

library(ggplot2)
SD4_NHIS_Data <- read_csv("Downloads/SD4 NHIS Data.csv")

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   health = col_double(),
##   sex = col_double(),
##   bmi = col_double()
## )

attach(SD4_NHIS_Data)
head(SD4_NHIS_Data)

## # A tibble: 6 x 3
##   health   sex   bmi
##    <dbl> <dbl> <dbl>
## 1      3     1  33.4
## 2      1     2  20.2
## 3      3     1  27.3
## 4      3     2  38.6
## 5      1     2  40.0
## 6      2     2  18.8

HealthSexBMI<-SD4_NHIS_Data%>%
  mutate(Health=ifelse(health==1, "Excellent",
                       ifelse(health==2,"Very Good",
                              ifelse(health==3, "Good",
                                     ifelse(health==4, "Fair",
                                            ifelse(health==5, "Poor",NA))))),
         Sex=ifelse(sex==1, "Male",
                     ifelse(sex==2, "Female", NA)),
          BMI=ifelse(bmi==0, NA,bmi),
           BMI=ifelse(bmi>=9999, NA,bmi))%>%
  filter(!is.na(Health),!is.na(Sex),!is.na(BMI))

HealthSexBMI

## # A tibble: 31,887 x 6
##    health   sex   bmi Health    Sex      BMI
##     <dbl> <dbl> <dbl> <chr>     <chr>  <dbl>
##  1      3     1  33.4 Good      Male    33.4
##  2      1     2  20.2 Excellent Female  20.2
##  3      3     1  27.3 Good      Male    27.3
##  4      3     2  38.6 Good      Female  38.6
##  5      1     2  40.0 Excellent Female  40.0
##  6      2     2  18.8 Very Good Female  18.8
##  7      2     2  19.7 Very Good Female  19.7
##  8      3     2  26.2 Good      Female  26.2
##  9      2     2  20.4 Very Good Female  20.4
## 10      1     2  23.0 Excellent Female  23.0
## # … with 31,877 more rows

Data Summaries

% of people in each Health category

table(HealthSexBMI$Health)%>%
  prop.table()%>%
  round(2)

## 
## Excellent      Fair      Good      Poor Very Good 
##      0.25      0.11      0.27      0.03      0.34

% of people of each Sex

table(HealthSexBMI$Sex)%>%
  prop.table()%>%
  round(2)

## 
## Female   Male 
##   0.54   0.46

Mean BMI

HealthSexBMI%>%
  summarize(meanBMI=mean(BMI,na.rm=TRUE))

## # A tibble: 1 x 1
##   meanBMI
##     <dbl>
## 1    28.0